vidhunnan/agentic-skills

Suggests and optionally creates a git branch name following the project's convention.

Documents every substantive commit into per-commit changelog files plus a rolling CHANGELOG index.

Mines a project for the decisions that were actually made and writes each as a numbered ADR with its evidence — asking when the "why" was never written down, and never inventing one.

Interviews you into a short, structured design brief — problem, who feels it, jobs to be done, constraints, success criteria and non-goals — and marks what wasn't stated rather than inventing it.

Reviews a built interface against its stated design intent — naming how the thing reads before proposing a fix, ranking findings by severity, and treating removal as a first-class verdict. Refuses to critique without a written intent.

Records a design fork as a numbered, append-only ADR — options, what was chosen, what was given up, and what would make us revisit — and never invents a rationale.

Generates three genuinely distinct design directions from a written visual direction — each committed to a named structural axis, each with its thesis, bet and risk — ending in a comparison matrix you judge by eye. Never records the verdict.

Interviews you into a written visual direction — the surface and its brand posture, the references and the anti-reference, the constraints as breakable rules, and the vocabulary — and asks what you want rather than proposing a look for you.

Scaffolds a project's design context stack — briefs, research, explorations, decisions, specs, system — and registers the routing table in CLAUDE.md.

Records a round of design iteration — what it tested, what changed, what was learned, and whether it was kept, killed or parked — append-only, and answers "have we tried this before?" from the log.

Interactive, bidirectional Chat↔Code generator for a comprehensive project handoff — progress, features, decisions, changelog, next actions, and a near-verbatim session log.

Creates and maintains docs/MODEL-STRATEGY.md — which Claude model to use for which work, tailored via interview.

Proposes three or four sourced angles worth posting from your material backlog and the record — each with its tension, its reader and its weakest point. Declines when nothing is worth a post yet.

Renders a post's visual plan into self-contained HTML frames at real dimensions, rasterised where a browser exists — from a direction you chose, and never stating what the post declined to claim.

Captures postable material while the work is warm — typed, indexed backlog items with the before-state snapshotted before it is overwritten. Never invents a learning.

Drafts per-platform copy from a sourced angle in your captured voice, decides how the post breaks into frames, and lists what it refused to claim and why. Never publishes.

Scaffolds the posts tier and captures how your posts should sound — by interview plus real samples — with personal profiles gitignored by default. The skill ships a template and never a voice.

Scaffolds a project's context stack — the tiered docs folders that let an agent be briefed on a project — and registers the routing table in CLAUDE.md.

Generates a new skill in this library's conventions — PRD, SKILL.md skeleton, plugin.json, marketplace entry, README row and website entry — from a short interview.

Splits the released version from the build you're testing, checks every file carrying the version agrees, and keeps a generated ledger of every build and release — across npm, Claude Code plugins, Docker, PyPI, binaries, sites, extensions, mobile apps and plain exports.